From patchwork Mon Jun 6 14:06:55 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Kirill A . Shutemov" X-Patchwork-Id: 9158283 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 68DBB60572 for ; Mon, 6 Jun 2016 14:19:48 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 503EE1FF21 for ; Mon, 6 Jun 2016 14:19:48 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 44E1A24B44; Mon, 6 Jun 2016 14:19:48 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=unavailable version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 37B1E1FF21 for ; Mon, 6 Jun 2016 14:19:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751908AbcFFOTb (ORCPT ); Mon, 6 Jun 2016 10:19:31 -0400 Received: from mga04.intel.com ([192.55.52.120]:45757 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752239AbcFFOHa (ORCPT ); Mon, 6 Jun 2016 10:07:30 -0400 Received: from orsmga001.jf.intel.com ([10.7.209.18]) by fmsmga104.fm.intel.com with ESMTP; 06 Jun 2016 07:07:29 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.26,427,1459839600"; d="scan'208";a="969839575" Received: from black.fi.intel.com ([10.237.72.93]) by orsmga001.jf.intel.com with ESMTP; 06 Jun 2016 07:07:25 -0700 Received: by black.fi.intel.com (Postfix, from userid 1000) id A5C1B903; Mon, 6 Jun 2016 17:07:14 +0300 (EEST) From: "Kirill A. Shutemov" To: Hugh Dickins , Andrea Arcangeli , Andrew Morton Cc: Dave Hansen , Vlastimil Babka , Christoph Lameter , Naoya Horiguchi , Jerome Marchand , Yang Shi , Sasha Levin , Andres Lagar-Cavilla , Ning Qu , linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, "Kirill A. Shutemov" Subject: [PATCHv9 18/32] radix-tree: implement radix_tree_maybe_preload_order() Date: Mon, 6 Jun 2016 17:06:55 +0300 Message-Id: <1465222029-45942-19-git-send-email-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 2.8.1 In-Reply-To: <1465222029-45942-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1465222029-45942-1-git-send-email-kirill.shutemov@linux.intel.com> Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The new helper is similar to radix_tree_maybe_preload(), but tries to preload number of nodes required to insert (1 << order) continuous naturally-aligned elements. This is required to push huge pages into pagecache. Signed-off-by: Kirill A. Shutemov --- include/linux/radix-tree.h | 1 + lib/radix-tree.c | 84 +++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 80 insertions(+), 5 deletions(-) diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index cb4b7e8cee81..084965cf90fc 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -291,6 +291,7 @@ unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); +int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8b7d8459bb9d..61b8fb529cef 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -38,6 +38,9 @@ #include /* in_interrupt() */ +/* Number of nodes in fully populated tree of given height */ +static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; + /* * Radix tree node cache. */ @@ -342,7 +345,7 @@ radix_tree_node_free(struct radix_tree_node *node) * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ -static int __radix_tree_preload(gfp_t gfp_mask) +static int __radix_tree_preload(gfp_t gfp_mask, int nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; @@ -350,14 +353,14 @@ static int __radix_tree_preload(gfp_t gfp_mask) preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); - while (rtp->nr < RADIX_TREE_PRELOAD_SIZE) { + while (rtp->nr < nr) { preempt_enable(); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); - if (rtp->nr < RADIX_TREE_PRELOAD_SIZE) { + if (rtp->nr < nr) { node->private_data = rtp->nodes; rtp->nodes = node; rtp->nr++; @@ -383,7 +386,7 @@ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); - return __radix_tree_preload(gfp_mask); + return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); @@ -395,7 +398,7 @@ EXPORT_SYMBOL(radix_tree_preload); int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) - return __radix_tree_preload(gfp_mask); + return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ preempt_disable(); return 0; @@ -403,6 +406,51 @@ int radix_tree_maybe_preload(gfp_t gfp_mask) EXPORT_SYMBOL(radix_tree_maybe_preload); /* + * The same as function above, but preload number of nodes required to insert + * (1 << order) continuous naturally-aligned elements. + */ +int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) +{ + unsigned long nr_subtrees; + int nr_nodes, subtree_height; + + /* Preloading doesn't help anything with this gfp mask, skip it */ + if (!gfpflags_allow_blocking(gfp_mask)) { + preempt_disable(); + return 0; + } + + /* + * Calculate number and height of fully populated subtrees it takes to + * store (1 << order) elements. + */ + nr_subtrees = 1 << order; + for (subtree_height = 0; nr_subtrees > RADIX_TREE_MAP_SIZE; + subtree_height++) + nr_subtrees >>= RADIX_TREE_MAP_SHIFT; + + /* + * The worst case is zero height tree with a single item at index 0 and + * then inserting items starting at ULONG_MAX - (1 << order). + * + * This requires RADIX_TREE_MAX_PATH nodes to build branch from root to + * 0-index item. + */ + nr_nodes = RADIX_TREE_MAX_PATH; + + /* Plus branch to fully populated subtrees. */ + nr_nodes += RADIX_TREE_MAX_PATH - subtree_height; + + /* Root node is shared. */ + nr_nodes--; + + /* Plus nodes required to build subtrees. */ + nr_nodes += nr_subtrees * height_to_maxnodes[subtree_height]; + + return __radix_tree_preload(gfp_mask, nr_nodes); +} + +/* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) @@ -1571,6 +1619,31 @@ radix_tree_node_ctor(void *arg) INIT_LIST_HEAD(&node->private_list); } +static __init unsigned long __maxindex(unsigned int height) +{ + unsigned int width = height * RADIX_TREE_MAP_SHIFT; + int shift = RADIX_TREE_INDEX_BITS - width; + + if (shift < 0) + return ~0UL; + if (shift >= BITS_PER_LONG) + return 0UL; + return ~0UL >> shift; +} + +static __init void radix_tree_init_maxnodes(void) +{ + unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH + 1]; + unsigned int i, j; + + for (i = 0; i < ARRAY_SIZE(height_to_maxindex); i++) + height_to_maxindex[i] = __maxindex(i); + for (i = 0; i < ARRAY_SIZE(height_to_maxnodes); i++) { + for (j = i; j > 0; j--) + height_to_maxnodes[i] += height_to_maxindex[j - 1] + 1; + } +} + static int radix_tree_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -1597,5 +1670,6 @@ void __init radix_tree_init(void) sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); + radix_tree_init_maxnodes(); hotcpu_notifier(radix_tree_callback, 0); }